Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1989 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.5957. Min Range: -8.5957
Max Act: 8.5957. Min Act: -0.1700
Data Index: 7893344 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.5957. Min Range: -8.5957
Max Act: 8.2207. Min Act: -0.1700
Data Index: 1393010 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.5957. Min Range: -8.5957
Max Act: 8.1582. Min Act: -0.1700
Data Index: 1638888 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.5957. Min Range: -8.5957
Max Act: 8.0957. Min Act: -0.1700
Data Index: 1941764 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.5957. Min Range: -8.5957
Max Act: 8.0332. Min Act: -0.1700
Data Index: 8134112 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.5957. Min Range: -8.5957
Max Act: 8.0957. Min Act: -0.1700
Data Index: 1758677 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.5957. Min Range: -8.5957
Max Act: 7.9707. Min Act: -0.1700
Data Index: 8280006 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.5957. Min Range: -8.5957
Max Act: 7.9707. Min Act: -0.1700
Data Index: 1693970 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.5957. Min Range: -8.5957
Max Act: 7.9082. Min Act: -0.1700
Data Index: 6132364 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.5957. Min Range: -8.5957
Max Act: 7.9707. Min Act: -0.1700
Data Index: 6554280 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.5957. Min Range: -8.5957
Max Act: 7.9082. Min Act: -0.1700
Data Index: 7973601 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.5957. Min Range: -8.5957
Max Act: 7.9082. Min Act: -0.1700
Data Index: 1749398 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.5957. Min Range: -8.5957
Max Act: 7.8457. Min Act: -0.1700
Data Index: 7085560 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.5957. Min Range: -8.5957
Max Act: 7.8457. Min Act: -0.1700
Data Index: 8561377 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.5957. Min Range: -8.5957
Max Act: 7.8457. Min Act: -0.1700
Data Index: 4066995 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.5957. Min Range: -8.5957
Max Act: 7.9082. Min Act: -0.1700
Data Index: 341455 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.5957. Min Range: -8.5957
Max Act: 7.8145. Min Act: -0.1700
Data Index: 5736442 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.5957. Min Range: -8.5957
Max Act: 7.8145. Min Act: -0.1700
Data Index: 5223103 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.5957. Min Range: -8.5957
Max Act: 7.8145. Min Act: -0.1700
Data Index: 1671184 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.5957. Min Range: -8.5957
Max Act: 7.8145. Min Act: -0.1700
Data Index: 1596089 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19